Bibliographic Details
| Title: |
Single-Channel Blind Image Separation Based on Transformer-Guided GAN |
| Authors: |
Yaya Su, Dongli Jia, Yankun Shen, Lin Wang |
| Source: |
Sensors, Vol 23, Iss 10, p 4638 (2023) |
| Publisher Information: |
MDPI AG, 2023. |
| Publication Year: |
2023 |
| Collection: |
LCC:Chemical technology |
| Subject Terms: |
blind image separation, generative adversarial network, Transformer, UNet, Chemical technology, TP1-1185 |
| More Details: |
Blind source separation (BSS) has been a great challenge in the field of signal processing due to the unknown distribution of the source signal and the mixing matrix. Traditional methods based on statistics and information theory use prior information such as source distribution independence, non-Gaussianity, sparsity, etc. to solve this problem. Generative adversarial networks (GANs) learn source distributions through games without being constrained by statistical properties. However, the current blind image separation methods based on GANs ignores the reconstruction of the structure and details of the separated image, resulting in residual interference source information in the generated results. This paper proposes a Transformer-guided GAN guided by an attention mechanism. Through the adversarial training of the generator and the discriminator, U-shaped Network (UNet) is used to fuse the convolutional layer features to reconstruct the structure of the separated image, and Transformer is used to calculate the position attention and guide the detailed information. We validate our method with quantitative experiments, showing that it outperforms previous blind image separation algorithms in terms of PSNR and SSIM. |
| Document Type: |
article |
| File Description: |
electronic resource |
| Language: |
English |
| ISSN: |
1424-8220 |
| Relation: |
https://www.mdpi.com/1424-8220/23/10/4638; https://doaj.org/toc/1424-8220 |
| DOI: |
10.3390/s23104638 |
| Access URL: |
https://doaj.org/article/2867dfc8f5654b12b10f6969597d7cde |
| Accession Number: |
edsdoj.2867dfc8f5654b12b10f6969597d7cde |
| Database: |
Directory of Open Access Journals |
|
Full text is not displayed to guests. |
Login for full access.
|
